From 8a6b8b91427a3de8fa96ff355af7f3e553093e22 Mon Sep 17 00:00:00 2001
From: njzjz-bot <njzjz.bot@gmail.com>
Date: Thu, 16 Jul 2026 11:54:33 +0800
Subject: [PATCH 1/2] fix(system): isolate sliced system metadata

Deep-copy both frame-selected arrays and frame-independent metadata when creating a subsystem so slice views and mutable values cannot alias the source. Add regressions for coordinates, cells, names, and atom types, which existing comparison tests did not mutate.

Coding-Agent: Codex
Codex-Version: codex-cli 0.144.4
Model: gpt-5.6-sol
Reasoning-Effort: xhigh
---
 dpdata/system.py            | 12 +++++++++---
 tests/test_system_append.py | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/dpdata/system.py b/dpdata/system.py
index 18b16aaf8..1c0425c45 100644
--- a/dpdata/system.py
+++ b/dpdata/system.py
@@ -461,10 +461,16 @@ def sub_system(self, f_idx: int | slice | list | np.ndarray):
                     slice(None) for _ in self.data[tt.name].shape
                 ]
                 new_shape[axis_nframes] = f_idx
-                tmp.data[tt.name] = self.data[tt.name][tuple(new_shape)]
+                # A slice produces a NumPy view, while advanced indexing
+                # produces a copy.  Deep-copy the result so ownership is
+                # consistent for every supported frame selector.
+                tmp.data[tt.name] = deepcopy(self.data[tt.name][tuple(new_shape)])
             else:
-                # keep the original data
-                tmp.data[tt.name] = self.data[tt.name]
+                # Frame-independent values (atom names/types, ``orig``, and
+                # optional metadata) are usually lists or arrays.  Copy them
+                # as well as frame data so editing a slice can never mutate
+                # the source system through a shared mutable object.
+                tmp.data[tt.name] = deepcopy(self.data[tt.name])
         return tmp
 
     def append(self, system: System) -> bool:
diff --git a/tests/test_system_append.py b/tests/test_system_append.py
index 7c325113f..5bd0aafd8 100644
--- a/tests/test_system_append.py
+++ b/tests/test_system_append.py
@@ -18,6 +18,41 @@ def test_failed_append(self):
         )
 
 
+class TestAppendOwnership(unittest.TestCase):
+    """Regression tests for copy-on-slice and copy-on-first-append semantics."""
+
+    def test_sub_system_does_not_alias_metadata(self):
+        system = dpdata.System(
+            data={
+                "atom_names": ["H"],
+                "atom_numbs": [1],
+                "atom_types": np.array([0]),
+                "orig": np.zeros(3),
+                "cells": np.eye(3).reshape(1, 3, 3),
+                "coords": np.zeros((1, 1, 3)),
+            }
+        )
+        sub = system[0:1]
+        sub.data["atom_names"][0] = "X"
+        sub.data["atom_types"][0] = 1
+        sub.data["coords"][0, 0, 0] = 123.0
+        sub.data["cells"][0, 0, 0] = 456.0
+        self.assertEqual(system.data["atom_names"], ["H"])
+        np.testing.assert_array_equal(system.data["atom_types"], [0])
+        self.assertEqual(system.data["coords"][0, 0, 0], 0.0)
+        self.assertEqual(system.data["cells"][0, 0, 0], 1.0)
+
+    def test_first_append_does_not_alias_source(self):
+        source = dpdata.System("poscars/POSCAR.oh.d", fmt="vasp/poscar")
+        target = dpdata.System()
+        target.append(source)
+
+        source.data["atom_names"][0] = "X"
+        source.data["coords"][0, 0, 0] = 123.0
+        self.assertEqual(target.data["atom_names"][0], "O")
+        self.assertNotEqual(target.data["coords"][0, 0, 0], 123.0)
+
+
 class TestVaspXmlAppend(unittest.TestCase, CompLabeledSys, IsPBC):
     def setUp(self):
         self.places = 6

From 527e2d4ab55bcb7676d36994f2cd1e559bc5e043 Mon Sep 17 00:00:00 2001
From: njzjz-bot <njzjz.bot@gmail.com>
Date: Tue, 21 Jul 2026 14:07:29 +0800
Subject: [PATCH 2/2] fix(system): deep-copy first appended system

Prevent the first append into an empty System from retaining aliases to the source system's nested metadata and arrays.

Coding-Agent: Codex
Codex-Version: codex-cli 0.144.6
Model: gpt-5.6-sol
Reasoning-Effort: xhigh
---
 dpdata/system.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/dpdata/system.py b/dpdata/system.py
index 1c0425c45..3c17299dd 100644
--- a/dpdata/system.py
+++ b/dpdata/system.py
@@ -486,7 +486,9 @@ def append(self, system: System) -> bool:
             return False
         elif not len(self.data["atom_numbs"]):
             # this system is non-converged but the system to append is converged
-            self.data = system.data.copy()
+            # Take ownership of every nested array/list just as sub_system
+            # does; a shallow dictionary copy would still alias the source.
+            self.data = deepcopy(system.data)
             return False
         if system.uniq_formula != self.uniq_formula:
             raise RuntimeError(